文章基本信息

标题：Dialog History Construction with Long-Short Term Memory for Robust Generative Dialog State Tracking
本地全文：下载
作者：Byung-Jun Lee ; Kee-Eung Kim
期刊名称：Dialogue and Discourse
电子版ISSN：2152-9620
出版年度：2016
卷号：7
期号：3
页码：47-64
DOI：10.5087/dad.2016.302
出版社：Linguistic Society of America
摘要：One of the crucial components of dialog system is the dialog state tracker, which infers user’s intention from preliminary speech processing. Since the overall performance of the dialog system is heavily affected by that of the dialog tracker, it has been one of the core areas of research on dialog systems. In this paper, we present a dialog state tracker that combines a generative probabilistic model of dialog state tracking with the recurrent neural network for encoding important aspects of the dialog history. We describe a two-step gradient descent algorithm that optimizes the tracker with a complex loss function. We demonstrate that this approach yields a dialog state tracker that performs competitively with top-performing trackers participated in the first and second Dialog State Tracking Challenges.
关键词：Dialog State Tracking;Dialog Management;Spoken Dialog System (SDS);Hidden Information State (HIS);Long Short Term Memory (LSTM).